Recently, graph neural networks (GNNs) have been successfully applied to predicting molecular properties, which is one of the most classical cheminformatics tasks with various applications. Despite their effectiveness, we empirically observe that training a single GNN model for diverse molecules with distinct structural patterns limits its prediction performance. In this paper, motivated by this observation, we propose TopExpert to leverage topology-specific prediction models (referred to as experts), each of which is responsible for each molecular group sharing similar topological semantics. That is, each expert learns topology-specific discriminative features while being trained with its corresponding topological group. To tackle the key challenge of grouping molecules by their topological patterns, we introduce a clustering-based gating module that assigns an input molecule into one of the clusters and further optimizes the gating module with two different types of self-supervision: topological semantics induced by GNNs and molecular scaffolds, respectively. Extensive experiments demonstrate that TopExpert has boosted the performance for molecular property prediction and also achieved better generalization for new molecules with unseen scaffolds than baselines. The code is available at https://github.com/kimsu55/ToxExpert.
Topology-Aware Multiscale Mixture of Experts for Efficient Molecular Property Prediction
School of Mathematics and Statistics（数学与统计学学院）；Victoria University of Wellington（威灵顿维多利亚大学）；School of Physical and Mathematical Sciences（物理与数学科学学院）；Nanyang Technological University（南洋理工大学）
Adaptive Substructure-Aware Expert Model for Molecular Property Prediction
Institute of Cyberspace Security, College of Information Engineering（信息工程学院网络空间安全研究所）；Binjiang Institute of Artificial Intelligence（滨江人工智能研究所）；Zhejiang University of Technology（浙江工业大学）
